Mobile video analysis with machine learning is 90% accurate in identifying a child with autism from home videos. This is more accurate than an average accuracy of human evaluators between 69.7% for a single evaluator, to 76.9% for nine evaluators. These findings were reported in "Mobile Detection Of Autism Through Machine Learning On Home Video: A Development And Prospective Validation Study" by Qandeel Tariq, Jena Daniels, Jessey Nicole Schwartz, Peter Washington, Haik Kalantarian, and Dennis Paul Wall. The researchers applied eight machine-learning models to 162 two-minute mobile device videos of children involved in parent-directed interviews . . .